{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T13:44:54Z","timestamp":1759412694834,"version":"build-2065373602"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T00:00:00Z","timestamp":1759017600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T00:00:00Z","timestamp":1759017600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11432-024-4603-x","type":"journal-article","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T11:32:04Z","timestamp":1759404724000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Consistent multimodal pre-training for visual tokenization"],"prefix":"10.1007","volume":"68","author":[{"given":"Ting","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lulu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,28]]},"reference":[{"key":"4603_CR1","volume-title":"Proceedings of International Conference on Machine Learning","author":"A Radford","year":"2021","unstructured":"Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision. In: Proceedings of International Conference on Machine Learning, 2021"},{"key":"4603_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"X Zhai","year":"2023","unstructured":"Zhai X, Mustafa B, Kolesnikov A, et al. Sigmoid loss for language image pre-training. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2023"},{"key":"4603_CR3","volume-title":"EVA-CLIP: improved training techniques for clip at scale","author":"Q Sun","year":"2023","unstructured":"Sun Q, Fang Y, Wu L, et al. EVA-CLIP: improved training techniques for clip at scale. 2023. ArXiv:2303.15389"},{"key":"4603_CR4","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Chen","year":"2024","unstructured":"Chen Z, Wu J, Wang W, et al. Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024"},{"key":"4603_CR5","volume-title":"Proceedings of International Conference on Learning Representations","author":"Q Sun","year":"2024","unstructured":"Sun Q, Yu Q, Cui Y, et al. Emu: generative pretraining in multimodality. In: Proceedings of International Conference on Learning Representations, 2024"},{"key":"4603_CR6","volume-title":"Generative multimodal models are in-context learners","author":"Q Sun","year":"2023","unstructured":"Sun Q, Cui Y, Zhang X, et al. Generative multimodal models are in-context learners. 2023. ArXiv:2312.13286"},{"key":"4603_CR7","doi-asserted-by":"publisher","first-page":"220101","DOI":"10.1007\/s11432-024-4231-5","volume":"67","author":"Z Chen","year":"2024","unstructured":"Chen Z, Wang W Y, Tian H, et al. How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites. Sci China Inf Sci, 2024, 67: 220101","journal-title":"Sci China Inf Sci"},{"key":"4603_CR8","volume-title":"DINOv2: learning robust visual features without supervision","author":"M Oquab","year":"2024","unstructured":"Oquab M, Darcet T, Moutakanni T, et al. DINOv2: learning robust visual features without supervision. 2024. ArXiv:2304.07193"},{"key":"4603_CR9","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"A Kirillov","year":"2023","unstructured":"Kirillov A, Mintun E, Ravi N, et al. Segment anything. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2023"},{"key":"4603_CR10","volume-title":"Proceedings of European Conference on Computer Vision","author":"H Wei","year":"2024","unstructured":"Wei H, Kong L, Chen J, et al. Vary: scaling up the vision vocabulary for large vision-language model. In: Proceedings of European Conference on Computer Vision, 2024"},{"key":"4603_CR11","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Tong","year":"2024","unstructured":"Tong S, Liu Z, Zhai Y, et al. Eyes wide shut? Exploring the visual shortcomings of multimodal LLMs. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024"},{"key":"4603_CR12","volume-title":"DeepSeek-vl: towards real-world vision-language understanding","author":"H Lu","year":"2024","unstructured":"Lu H, Liu W, Zhang B, et al. DeepSeek-vl: towards real-world vision-language understanding. 2024. ArXiv:2403.05525"},{"key":"4603_CR13","volume-title":"From clip to dino: visual encoders shout in multi-modal large language models","author":"D Jiang","year":"2023","unstructured":"Jiang D, Liu Y, Liu S, et al. From clip to dino: visual encoders shout in multi-modal large language models. 2023. ArXiv:2310.08825"},{"key":"4603_CR14","volume-title":"Proceedings of International Conference on Machine Learning","author":"S Karamcheti","year":"2024","unstructured":"Karamcheti S, Nair S, Balakrishna A, et al. Prismatic VLMs: investigating the design space of visually-conditioned language models. In: Proceedings of International Conference on Machine Learning, 2024"},{"key":"4603_CR15","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"H Liu","year":"2024","unstructured":"Liu H, Li C, Li Y, et al. Improved baselines with visual instruction tuning. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024"},{"key":"4603_CR16","volume-title":"Proceedings of European Conference on Computer Vision","author":"B Shi","year":"2024","unstructured":"Shi B, Wu Z, Mao M, et al. When do we not need larger vision models? In: Proceedings of European Conference on Computer Vision, 2024"},{"key":"4603_CR17","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"X Dong","year":"2024","unstructured":"Dong X, Zhang P, Zang Y, et al. InternLM-XComposer2-4KHD: a pioneering large vision-language model handling resolutions from 336 pixels to 4k HD. In: Proceedings of Conference on Neural Information Processing Systems, 2024"},{"key":"4603_CR18","volume-title":"Laion-5b: an open large-scale dataset for training next generation image-text models","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann C, Beaumont R, Vencu R, et al. Laion-5b: an open large-scale dataset for training next generation image-text models. 2022. ArXiv:2210.08402"},{"key":"4603_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O, et al. Visual Genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis, 2017, 123: 32\u201373","journal-title":"Int J Comput Vis"},{"key":"4603_CR20","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Huang X, Ma J, et al. Recognize anything: a strong image tagging model. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024"},{"key":"4603_CR21","volume-title":"Proceedings of International Conference on Learning Representations","author":"W Wang","year":"2024","unstructured":"Wang W, Shi M, Li Q, et al. The all-seeing project: towards panoptic visual recognition and understanding of the open world. In: Proceedings of International Conference on Learning Representations, 2024"},{"key":"4603_CR22","first-page":"36","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"H Liu","year":"2024","unstructured":"Liu H, Li C, Wu Q, et al. Visual instruction tuning. In: Proceedings of Advances in Neural Information Processing Systems, 2024. 36"},{"key":"4603_CR23","volume-title":"Proceedings of European Conference on Computer Vision","author":"L Chen","year":"2024","unstructured":"Chen L, Li J, Dong X, et al. ShareGPT4V: improving large multi-modal models with better captions. In: Proceedings of European Conference on Computer Vision, 2024"},{"key":"4603_CR24","volume-title":"Efficient multimodal learning from data-centric perspective","author":"M He","year":"2024","unstructured":"He M, Liu Y, Wu B, et al. Efficient multimodal learning from data-centric perspective. 2024. ArXiv:2402.11530"},{"key":"4603_CR25","volume-title":"Proceedings of European Conference on Computer Vision","author":"T Y Lin","year":"2014","unstructured":"Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: common objects in context. In: Proceedings of European Conference on Computer Vision, 2014"},{"key":"4603_CR26","volume-title":"GPT-4 technical report","author":"J Achiam","year":"2023","unstructured":"Achiam J, Adler S, Agarwal S, et al. GPT-4 technical report. 2023. ArXiv:2303.08774"},{"key":"4603_CR27","volume-title":"GPT-4v (ision) system card","author":"OpenAI.","year":"2023","unstructured":"OpenAI. GPT-4v (ision) system card. 2023. https:\/\/openai.com\/index\/gpt-4v-system-card"},{"key":"4603_CR28","volume-title":"SVIT: scaling up visual instruction tuning","author":"B Zhao","year":"2023","unstructured":"Zhao B, Wu B, Huang T. SVIT: scaling up visual instruction tuning. 2023. ArXiv:2307.04087"},{"key":"4603_CR29","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Gupta","year":"2019","unstructured":"Gupta A, Dollar P, Girshick R. LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019"},{"key":"4603_CR30","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"D A Hudson","year":"2019","unstructured":"Hudson D A, Manning C D. GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019"},{"key":"4603_CR31","volume-title":"SEED-Bench: benchmarking multimodal LLMs with generative comprehension","author":"B Li","year":"2023","unstructured":"Li B, Wang R, Wang G, et al. SEED-Bench: benchmarking multimodal LLMs with generative comprehension. 2023. ArXiv:2307.16125"},{"key":"4603_CR32","volume-title":"Proceedings of International Conference on Machine Learning","author":"C Jia","year":"2021","unstructured":"Jia C, Yang Y, Xia Y, et al. Scaling up visual and vision-language representation learning with noisy text supervision. In: Proceedings of International Conference on Machine Learning, 2021"},{"key":"4603_CR33","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Li","year":"2023","unstructured":"Li Y, Fan H, Hu R, et al. Scaling language-image pre-training via masking. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023"},{"key":"4603_CR34","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Wang","year":"2023","unstructured":"Wang X, Wang W, Cao Y, et al. Images speak in images: a generalist painter for in-context visual learning. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023"},{"key":"4603_CR35","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"X Wang","year":"2023","unstructured":"Wang X, Zhang X, Cao Y, et al. SegGPT: towards segmenting everything in context. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2023"},{"key":"4603_CR36","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"X Zou","year":"2023","unstructured":"Zou X, Yang J, Zhang H, et al. Segment everything everywhere all at once. In: Proceedings of Conference on Neural Information Processing Systems, 2023"},{"key":"4603_CR37","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"J B Alayrac","year":"2022","unstructured":"Alayrac J B, Donahue J, Luc P, et al. Flamingo: a visual language model for few-shot learning. In: Proceedings of Conference on Neural Information Processing Systems, 2022"},{"key":"4603_CR38","volume-title":"Proceedings of International Conference on Learning Representations","author":"J Lu","year":"2023","unstructured":"Lu J, Clark C, Zellers R, et al. Unified-io: a unified model for vision, language, and multi-modal tasks. In: Proceedings of International Conference on Learning Representations, 2023"},{"key":"4603_CR39","volume-title":"SAM-CLIP: merging vision foundation models towards semantic and spatial understanding","author":"H Wang","year":"2023","unstructured":"Wang H, Vasu P K A, Faghri F, et al. SAM-CLIP: merging vision foundation models towards semantic and spatial understanding. 2023. ArXiv:2310.15308"},{"key":"4603_CR40","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"H Yang","year":"2024","unstructured":"Yang H, Ma C, Wen B, et al. Recognize any regions. In: Proceedings of Conference on Neural Information Processing Systems, 2024"},{"key":"4603_CR41","volume-title":"Proceedings of European Conference on Computer Vision","author":"F Li","year":"2024","unstructured":"Li F, Zhang H, Sun P, et al. Segment and recognize anything at any granularity. In: Proceedings of European Conference on Computer Vision, 2024"},{"key":"4603_CR42","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Zou","year":"2023","unstructured":"Zou X, Dou Z Y, Yang J, et al. Generalized decoding for pixel, image, and language. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023"},{"key":"4603_CR43","volume-title":"Proceedings of International Conference on Machine Learning","author":"J Li","year":"2023","unstructured":"Li J, Li D, Savarese S, et al. BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of International Conference on Machine Learning, 2023"},{"key":"4603_CR44","volume-title":"Proceedings of International Conference on Learning Representations","author":"D Zhu","year":"2024","unstructured":"Zhu D, Chen J, Shen X, et al. MiniGPT-4: enhancing vision-language understanding with advanced large language models. In: Proceedings of International Conference on Learning Representations, 2024"},{"key":"4603_CR45","volume-title":"Phi-2: the surprising power of small language models","author":"Microsoft.","year":"2023","unstructured":"Microsoft. Phi-2: the surprising power of small language models. https:\/\/www.microsoft.com\/en-us\/research\/blog\/phi-2-thesurprising-power-of-small-language-models, 2023"},{"key":"4603_CR46","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"L Zheng","year":"2023","unstructured":"Zheng L, Chiang W L, Sheng Y, et al. Judging LLM-as-a-judge with mt-bench and chatbot arena. In: Proceedings of Conference on Neural Information Processing Systems, 2023"},{"key":"4603_CR47","volume-title":"Proceedings of International Conference on Learning Representations","author":"A Dosovitskiy","year":"2020","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16SX16 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations, 2020"},{"key":"4603_CR48","volume-title":"Proceedings of European Conference on Computer Vision","author":"Y Li","year":"2022","unstructured":"Li Y, Mao H, Girshick R, et al. Exploring plain vision transformer backbones for object detection. In: Proceedings of European Conference on Computer Vision, 2022"},{"key":"4603_CR49","first-page":"4804","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Li","year":"2022","unstructured":"Li Y, Wu C Y, Fan H, et al. Mvitv2: improved multiscale vision transformers for classification and detection. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 4804\u20134814"},{"key":"4603_CR50","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"M Minderer","year":"2023","unstructured":"Minderer M, Gritsenko A, Houlsby N. Scaling open-vocabulary object detection. In: Proceedings of Conference on Neural Information Processing Systems, 2023"},{"key":"4603_CR51","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"T Y Lin","year":"2017","unstructured":"Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2017"},{"key":"4603_CR52","volume-title":"Proceedings of International Conference on 3D Vision","author":"F Milletari","year":"2016","unstructured":"Milletari F, Navab N, Ahmadi S, et al. Fully convolutional neural networks for volumetric medical image segmentation. In: Proceedings of International Conference on 3D Vision, 2016"},{"key":"4603_CR53","doi-asserted-by":"publisher","first-page":"127063","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su J, Ahmed M, Lu Y, et al. RoFormer: enhanced transformer with Rotary Position Embedding. Neurocomputing, 2024, 568: 127063","journal-title":"Neurocomputing"},{"key":"4603_CR54","volume-title":"Proceedings of Annual Meeting of the Association for Computational Linguistics","author":"R Sennrich","year":"2016","unstructured":"Sennrich R, Haddow B, Birch A. Neural machine translation of rare words with subword units. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, 2016"},{"key":"4603_CR55","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Cha","year":"2024","unstructured":"Cha J, Kang W, Mun J, et al. Honeybee: locality-enhanced projector for multimodal LLM. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024"},{"key":"4603_CR56","volume-title":"Mm1: methods, analysis & insights from multimodal llm pre-training","author":"B McKinzie","year":"2024","unstructured":"McKinzie B, Gan Z, Fauconnier J P, et al. Mm1: methods, analysis & insights from multimodal llm pre-training. 2024. ArXiv:2403.09611"},{"key":"4603_CR57","volume-title":"Proceedings of International Conference on Learning Representations","author":"E J Hu","year":"2022","unstructured":"Hu E J, Shen Y, Wallis P, et al. Lora: low-rank adaptation of large language models. In: Proceedings of International Conference on Learning Representations, 2022"},{"key":"4603_CR58","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"R A Jacobs","year":"1991","unstructured":"Jacobs R A, Jordan M I, Nowlan S J, et al. Adaptive mixtures of local experts. Neural Comput, 1991, 3: 79\u201387","journal-title":"Neural Comput"},{"key":"4603_CR59","volume-title":"Proceedings of Conference on Neural Information Processing Systems","author":"L Yao","year":"2022","unstructured":"Yao L, Han J, Wen Y, et al. Detclip: dictionary-enriched visual-concept paralleled pre-training for open-world detection. In: Proceedings of Conference on Neural Information Processing Systems, 2022"},{"key":"4603_CR60","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Zhong","year":"2022","unstructured":"Zhong Y, Yang J, Zhang P, et al. Regionclip: region-based language-image pretraining. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022"},{"key":"4603_CR61","first-page":"633","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"B Zhou","year":"2017","unstructured":"Zhou B, Zhao H, Puig X, et al. Scene parsing through ade20k dataset. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2017. 633\u2013641"},{"key":"4603_CR62","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"S Shao","year":"2019","unstructured":"Shao S, Li Z, Zhang T, et al. Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, 2019"},{"key":"4603_CR63","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova A, Rom H, Alldrin N, et al. The open images dataset V4. Int J Comput Vis, 2020, 128: 1956\u20131981","journal-title":"Int J Comput Vis"},{"key":"4603_CR64","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Mao","year":"2016","unstructured":"Mao J, Huang J, Toshev A, et al. Generation and comprehension of unambiguous object descriptions. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2016"},{"key":"4603_CR65","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Goyal","year":"2017","unstructured":"Goyal Y, Khot T, Summers-Stay D, et al. Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2017"},{"key":"4603_CR66","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Singh","year":"2019","unstructured":"Singh A, Natarajan V, Shah M, et al. Towards VQA models that can read. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019"},{"key":"4603_CR67","volume-title":"Proceedings of European Conference on Computer Vision","author":"Y Liu","year":"2024","unstructured":"Liu Y, Duan H, Zhang Y, et al. MMBench: is your multi-modal model an all-around player? In: Proceedings of European Conference on Computer Vision, 2024"},{"key":"4603_CR68","volume-title":"Proceedings of International Conference on Learning Representations","author":"I Loshchilov","year":"2019","unstructured":"Loshchilov I, Hutter F. Decoupled weight decay regularization. In: Proceedings of International Conference on Learning Representations, 2019"},{"key":"4603_CR69","volume-title":"Proceedings of International Conference on Learning Representations","author":"I Loshchilov","year":"2017","unstructured":"Loshchilov I, Hutter F. Sgdr: stochastic gradient descent with warm restarts. In: Proceedings of International Conference on Learning Representations, 2017"},{"key":"4603_CR70","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"G Ghiasi","year":"2021","unstructured":"Ghiasi G, Cui Y, Srinivas A, et al. Simple copy-paste is a strong data augmentation method for instance segmentation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021"},{"key":"4603_CR71","volume-title":"Proceedings of European Conference on Computer Vision","author":"G Huang","year":"2016","unstructured":"Huang G, Sun Y, Liu Z, et al. Deep networks with stochastic depth. In: Proceedings of European Conference on Computer Vision, 2016"},{"key":"4603_CR72","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res, 2014, 15: 1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"4603_CR73","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2022","unstructured":"He K, Chen X, Xie S, et al. Masked autoencoders are scalable vision learners. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022"},{"key":"4603_CR74","volume-title":"Proceedings of European Conference on Computer Vision","author":"J Wu","year":"2024","unstructured":"Wu J, Wang J, Yang Z, et al. GRiT: a generative region-to-text transformer for object understanding. In: Proceedings of European Conference on Computer Vision, 2024"},{"key":"4603_CR75","volume-title":"GPT4ROI: instruction tuning large language model on region-of-interest","author":"S Zhang","year":"2023","unstructured":"Zhang S, Sun P, Chen S, et al. GPT4ROI: instruction tuning large language model on region-of-interest. 2023. ArXiv:2307.03601"},{"key":"4603_CR76","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Sun","year":"2024","unstructured":"Sun Z, Fang Y, Wu T, et al. Alpha-CLIP: a clip model focusing on wherever you want. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024"},{"key":"4603_CR77","volume-title":"Internchat: solving vision-centric tasks by interacting with chatbots beyond language","author":"Z Liu","year":"2023","unstructured":"Liu Z, He Y, Wang W, et al. Internchat: solving vision-centric tasks by interacting with chatbots beyond language. 2023. ArXiv:2305.05662"},{"key":"4603_CR78","volume-title":"OpenLLaMA: an open reproduction of LLaMA","author":"X Geng","year":"2023","unstructured":"Geng X, Liu H. OpenLLaMA: an open reproduction of LLaMA. 2023. https:\/\/www.microsoft.com\/en-us\/research\/blog\/phi-2-the-surprising-power-of-small-language-models"},{"key":"4603_CR79","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Huang","year":"2024","unstructured":"Huang X, Wang J, Tang Y, et al. Segment and caption anything. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4603-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4603-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4603-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T13:14:40Z","timestamp":1759410880000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4603-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,28]]},"references-count":79,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["4603"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4603-x","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"type":"print","value":"1674-733X"},{"type":"electronic","value":"1869-1919"}],"subject":[],"published":{"date-parts":[[2025,9,28]]},"assertion":[{"value":"15 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"200106"}}